USA: The technology of the future will undoubtedly make the search for life outside our planet easier. A new machine learning tool developed by researchers could be useful in the search for life on Mars and other extraterrestrial bodies.

In particular, the newly created instrument could have a significant impact on the current Mars exploration mission, the Perseverance rover, and other upcoming robotic missions.

There are currently very few opportunities to bring back samples from other planets. To search for signs of life on extraterrestrial worlds, researchers use remote sensing equipment, but gaining access to these instruments can be challenging.

Also Read: NASA's JWST senses an exoplanet's thermostat for the very first time

The challenges of the future for the scientific community may be a lot less daunting, thanks to the latest AI tools and their encouraging results.

Salar de Pajonales, a salt basin on the border of Chile's Atacama Desert and the Altiplano, a high plateau region, is where scientists mapped rare lifeforms found in salt domes, rocks and crystals.

The climate of Pajonales is thought to be similar to that of Mars because it is hyperarid, has a high UV index, and is located at an altitude of 3,541 m.

To identify the patterns and guidelines governing the distribution of life in these harsh environments, the researchers trained a machine learning model. The training gave the model the ability to find related patterns in the data that had not been found before.

Also Read: How to configure Twitter for app-based two factor authentication.

The system can detect and identify biosignature substances that can provide evidence of past or present life up to 87.5% of the time after combining statistical ecology with AI. In contrast random searches had a success rate of only 10% or more.

Additionally, the instrument can reduce the search area by up to 97%, helping scientists improve their search for extraterrestrial life.

The study's lead author, Kim Warren-Rhodes of the SETI Institute, said, "Our framework enables us to combine the power of statistical ecology with machine learning to discover and predict the patterns and rules by which nature lives. Lives and distributes itself in the toughest scenario on earth.

"We hope that other astronomy teams will use our method to map other habitable environments and biosignatures," the researchers write.

No matter how obscure or unusual, we can use these models to create custom roadmaps and algorithms to guide rovers to locations that have the highest probability of harboring past or present life.

According to researchers, the Perseverance rover searching for signs of life in Mars' Jezero Crater could use such machine learning tools.

More than 1,000 samples and 8,000 images were collected from the Salar de Pajonales by the team, who also tested instruments to look for photosynthetic microbes in the area's salt domes, rocks and alabaster crystals.

On NASA's "Ladder of Life Detection," which aims to guide investigations toward "detecting microbial life within the practical constraints of robotic space missions," the pigments emitted by these microbes represent a potential biosignature.

The teams found that the distribution of microbial life in the Salar de Pajonales was not random, using drone imagery. Rather, it was concentrated in biological hotspots closely related to water availability.

Also Read: Where and when to view Mercury, Jupiter, Venus, Uranus, and Mars as they align in the night sky

The team used the Salar de Pajonales to train convolutional neural networks (CNNs) to identify and predict large macro-scale geologic features.

Patterned ground and polygonal networks, two features of this region, are also found on Mars. Additionally, the system was trained to identify and predict small, micro-scale habitats most likely to contain biosignatures.